Contour detection method based on visual mechanism dark edge enhancement

Abstract

The invention relates to a contour detection method based on visual mechanism dark edge enhancement. The method comprises the following steps: firstly, simulating retina photoreceptor cell response characteristics, and proposing a dark field adjustment model based on local brightness characteristics; then, in combination with the scale orientation characteristic of the classical receptive field ofthe ganglion cells, obtaining a primary contour response, and extracting global contour information by utilizing a principal component analysis method; then, when a retinal ganglion signal is transmitted to an outer knee body, simulating a side inhibition effect of a non-classical receptive field, further introducing a nerve cell sparse response characteristic, and cooperatively inhibiting a background strong texture of a primary contour; simulating the enhancement effect of micro-motion information on contour perception understanding so that background weak textures are reduced, and then using adaptive dynamic synapses for outputting and transmitting external knee body impulse responses to a primary visual cortex; and finally, correcting the primary contour response through global contour information, and outputting and quickly fusing the corrected primary contour response with the primary visual cortex response to generate a more accurate and effective contour detection result.

Description

technical field [0001] The invention relates to the field of visual mechanism and image processing, in particular to a contour detection method based on dark edge enhancement of visual mechanism. Background technique [0002] Contour information, as a low-dimensional visual feature of image objects, will not only significantly affect the accuracy of subsequent image analysis and understanding, but also has great significance for reducing the complexity of the system from the input level. Traditional contour detection methods are often difficult to locate the contours of image objects with texture interference, especially for images with weak contrast or a large proportion of dark edges, texture suppression will lose a lot of real contour information at the same time. [0003] With the development of visual physiological experiments and computational neurology, various computational models based on visual mechanisms have been widely used in image contour extraction. For exam...

AI Technical Summary

Problems solved by technology

However, it must be pointed out that the above-mentioned contour extraction method based on the visual neural computing model usually only considers part of the transfer response process on the main visual pathway, ignores the retinal adjustment effect on dark edge stimuli, and simplifies the single main visual pathway. Multi-level processing capabilities of nodes

In addition, they did not consider the cross-view modulation effect of the front-level nodes on the visual cortex, weakening the interactive connection of visual information flow in the visual pathway, and reducing the ability of the visual system to express and understand image contour information

Images